Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77413
    Prev
    Next
    INDEX
    Explanations

    Watch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    berry
    -0.08
     terraz
    -0.07
     immortal
    -0.07
     midfield
    -0.07
     महत्व
    -0.07
     bruis
    -0.07
     ميز
    -0.07
     blush
    -0.07
     önem
    -0.07
     محور
    -0.07
    POSITIVE LOGITS
     Quran
    0.09
     Kumar
    0.08
     Sushi
    0.08
    .youtube
    0.08
     Mar
    0.08
     Sea
    0.08
    atan
    0.08
     podcasts
    0.08
    pg
    0.08
     eel
    0.07
    Activations Density 0.035%

    No Known Activations